Efficient mining of multiple partial near-duplicate alignments by temporal network
This paper considers the mining and localization of near-duplicate segments at arbitrary positions of partial near-duplicate videos in a corpus. Temporal network is proposed to model the visual-temporal consistency between video sequence by embedding temporal constraints as directed edges in the net...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2010
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6319 https://ink.library.smu.edu.sg/context/sis_research/article/7322/viewcontent/csvt_hktan_10.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-7322 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-73222021-11-23T05:12:23Z Efficient mining of multiple partial near-duplicate alignments by temporal network TAN, Hung-Khoon NGO, Chong-wah CHUA, Tat-Seng This paper considers the mining and localization of near-duplicate segments at arbitrary positions of partial near-duplicate videos in a corpus. Temporal network is proposed to model the visual-temporal consistency between video sequence by embedding temporal constraints as directed edges in the network. Partial alignment is then achieved through network flow programming. To handle multiple alignments, we consider two properties of network structure: conciseness and divisibility, to ensure that the mining is efficient and effective. Frame-level matching is further integrated in the temporal network for alignment verification. This results in an iterative alignment-verification procedure to fine tune the localization of near-duplicate segments. The scalability of frame-level matching is enhanced by exploring visual keyword matching algorithms. We demonstrate the proposed work for mining partial alignments from two months of broadcast videos and across six TV sources. 2010-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6319 info:doi/10.1109/TCSVT.2010.2077531 https://ink.library.smu.edu.sg/context/sis_research/article/7322/viewcontent/csvt_hktan_10.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Keyword matching Partial near-duplicate temporal graph Graphics and Human Computer Interfaces OS and Networks |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Keyword matching Partial near-duplicate temporal graph Graphics and Human Computer Interfaces OS and Networks |
spellingShingle |
Keyword matching Partial near-duplicate temporal graph Graphics and Human Computer Interfaces OS and Networks TAN, Hung-Khoon NGO, Chong-wah CHUA, Tat-Seng Efficient mining of multiple partial near-duplicate alignments by temporal network |
description |
This paper considers the mining and localization of near-duplicate segments at arbitrary positions of partial near-duplicate videos in a corpus. Temporal network is proposed to model the visual-temporal consistency between video sequence by embedding temporal constraints as directed edges in the network. Partial alignment is then achieved through network flow programming. To handle multiple alignments, we consider two properties of network structure: conciseness and divisibility, to ensure that the mining is efficient and effective. Frame-level matching is further integrated in the temporal network for alignment verification. This results in an iterative alignment-verification procedure to fine tune the localization of near-duplicate segments. The scalability of frame-level matching is enhanced by exploring visual keyword matching algorithms. We demonstrate the proposed work for mining partial alignments from two months of broadcast videos and across six TV sources. |
format |
text |
author |
TAN, Hung-Khoon NGO, Chong-wah CHUA, Tat-Seng |
author_facet |
TAN, Hung-Khoon NGO, Chong-wah CHUA, Tat-Seng |
author_sort |
TAN, Hung-Khoon |
title |
Efficient mining of multiple partial near-duplicate alignments by temporal network |
title_short |
Efficient mining of multiple partial near-duplicate alignments by temporal network |
title_full |
Efficient mining of multiple partial near-duplicate alignments by temporal network |
title_fullStr |
Efficient mining of multiple partial near-duplicate alignments by temporal network |
title_full_unstemmed |
Efficient mining of multiple partial near-duplicate alignments by temporal network |
title_sort |
efficient mining of multiple partial near-duplicate alignments by temporal network |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2010 |
url |
https://ink.library.smu.edu.sg/sis_research/6319 https://ink.library.smu.edu.sg/context/sis_research/article/7322/viewcontent/csvt_hktan_10.pdf |
_version_ |
1770575933569236992 |